Triple

T392035
Position Surface form Disambiguated ID Type / Status
Subject Johnny Most E8901 entity
Predicate nickname P55 FINISHED
Object Johnny Most E8901 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Johnny Most | Statement: [Johnny Most, nickname, Johnny Most]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johnny Most
Context triple: [Johnny Most, nickname, Johnny Most]
  • A. Johnny Most chosen
    Johnny Most was a legendary American sports broadcaster best known as the longtime, passionately partisan radio voice of the Boston Celtics.
  • B. Frank Howard
    Frank Howard was a towering power-hitting outfielder and first baseman of the 1960s and early 1970s, best known for his prodigious home runs and multiple All-Star seasons in Major League Baseball.
  • C. Jud Fry
    Jud Fry is the brooding, antagonistic farmhand and primary villain in the classic American musical "Oklahoma!".
  • D. Bill Kramer
    Bill Kramer is an American entrepreneur best known for establishing the iconic independent bookstore and café Kramerbooks & Afterwords Cafe in Washington, D.C.
  • E. Sam Jones
    Sam Jones was a Hall of Fame shooting guard who won 10 NBA championships with the Boston Celtics during the 1950s and 1960s, making him one of the most decorated players in league history.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a2e7f55c60819097aff65ea2ca2832 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec7492288190bf33c9c869a0710f completed Feb. 28, 2026, 1:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69a40ad425a881909eea63c64a683c0f completed March 1, 2026, 9:45 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.